Abstract: Artificial intelligence (AI) agents for user interface (UI) automation to application programming interface (API) automation, and vice versa, are disclosed. The operations performed by a UI automation on the back-end can be captured by an AI agent, including what communications are sent and the context thereof. A robotic process automation (RPA) activity can then be built in an RPA workflow that replaces the UI automation with an API automation. Alternatively, an API automation is replaced with a UI automation. The AI agent employs a fine-tuned generative AI model to understand the context of the communications. The AI agent may also find obsolete duplicates of UI automations and replace these with API automations, or vice versa.

Abstract: Systems and methods for updating an AI (artificial intelligence) agent are provided. Process lifeline data associated with one or more processes is received. Events are identified in the process lifeline data. The process lifeline data and the events are stored in a repository. The process lifeline data and the events are associated with particular processes of the one or more processes. The AI agent is updated based on the process lifeline data, the events, and the associations.

Abstract: A method is provided. The method is executed by a modeling engine implemented as a computer program within a computing environment. The method includes translating a pre-processed model based on an unstructured existing process into a patched process tree. The translating includes detecting, structuring, and translating rigids of the pre-processed model into corresponding process tree equivalent elements of the patched process tree.

Abstract: Generation of unified projects/solutions in artificial intelligence (AI) agent, robotic process automation (RPA) robot, and agentic orchestration process (AOP) development applications is disclosed. Based on a prompt, a process definition document, or some other source, an entire end-to-end business process can be automated, including underlying code and the requisite dependencies. A generative AI model is used to generate an AOP for the business process, including steps performed by AI agent(s) and/or RPA robot(s). The AOP may be represented in Business Process Model and Notation (BPMN), which is an Extensible Markup Language (XML) description of the business process. The designer application may also display a flowchart that shows the AOP. The generative AI model employed by the designer application is fine-tuned to understand which BPMN steps to include in the AOP, including steps that are executed by AI agents and/or RPA robots.

Abstract: Automatic generation of solutions for agentic automation for artificial intelligence (AI) agents, robotic process automation (RPA) robots, agentic orchestration processes (AOPs), and humans-in-the-loop using autopilots are disclosed. Autopilots can be used to generate an AOP for a business process, as well as AI agents and RPA robots for AOP steps used as parts. The AOP defines a business process (e.g., in Business Process Model and Notation (BPMN)). An AOP autopilot may first generate an AOP from a source, such as a prompt, document(s), a spreadsheet, a flowchart, etc. The AOP autopilot may then use AI agent autopilots and RPA autopilots to generate AI agents and RPA workflows for these AOP steps.

Abstract: Automatic generation of solutions for agentic automation for artificial intelligence (AI) agents, robotic process automation (RPA) robots, agentic orchestration processes (AOPs), and humans-in-the-loop using autopilots are disclosed. Autopilots can be used to generate an AOP for a business process, as well as AI agents and RPA robots for AOP steps used as parts. The AOP defines a business process (e.g., in Business Process Model and Notation (BPMN)). An AOP autopilot may first generate an AOP from a source, such as a prompt, document(s), a spreadsheet, a flowchart, etc. The AOP autopilot may then use AI agent autopilots and RPA autopilots to generate AI agents and RPA workflows for these AOP steps.

Abstract: Predictive healing artificial intelligence (AI) agents that preemptively detect impending workflow errors, failures, and/or faults and automatically attempt recovery are disclosed. The healing capabilities of the AI agents may be seamlessly integrated into existing systems and workflows with minimal disruption. A developer may build a user interface (UI) automation workflow that works at design time, but will fail at runtime for some reason. For instance, the automation may be deployed to a computing system with different graphical characteristics than those that were present when the automation was designed, a software update may change aspects of the UI, the computing system may be too busy to run the automation, there may be connectivity issues, a third party system that the automation relies upon may be down, etc. An AI agent can detect that these issues will occur when the automation is run and attempt to automatically correct them.

Abstract: Systems and methods for configuring an RPA (robotic process automation) platform to perform a candidate process automation are provided. Discovery data relating to a candidate process automation is generated. RPA platform design components for configuring an RPA platform to perform the candidate process automation are generated based on the discovery data. The RPA platform design components are presented to a user via a user interface.

Abstract: An agentic extraction method is provided. The agentic extraction method is implemented by artificial intelligence (AI) agents to generate and provide a context grounding for an AI model. The agentic extraction method includes extracting text data from documents including complex document structures and capturing images of the documents. The agentic extraction method includes performing a multistage processing of the text data and the images utilizing large language models to generate an output set including a contextualization and one or more keywords. The agentic extraction method includes converting the output set to vectors including context embeddings to provide the context grounding.

Abstract: An agentic searching method is provided. The agentic searching method is implemented by artificial intelligence (AI) agents. The agentic searching method includes performing advanced agentic searching of a sematic storage including context embeddings in response to a complex query. The agentic searching method includes outputting a context grounding resulting from the searching of the sematic storage and the context embeddings to an AI model with the complex query to enhance an accuracy of a response of the AI model. The agentic searching method includes receiving the response to the complex query from the AI model.

Abstract: An agentic memory method is provided. The agentic memory method is implemented by artificial intelligence (AI) agents. The agentic memory method includes storing vectors including context embeddings generated by advanced agentic extraction in response to queries in an agentic memory. The agentic memory method includes receiving and matching a complex query to the vectors of the agentic memory by an advanced agentic search to determine a context grounding. The agentic memory method includes providing the context grounding to an AI model with the complex query to enhance an accuracy of a response of the AI model and receiving the response to the complex query from the AI model.

Abstract: A system and method provide an integrated automation solution that links multiple systems and applications of a contact center operation and provides a unified support interface and unified knowledge base that delivers relevant data in real-time to assist contact center personnel during a customer interaction. Robotic Process Automation (RPA) is used for automating workflows and processes with robots (e.g., attended and/or unattended) that perform various tasks and activities for capturing information (data, documents, etc.) from multiple front-end and/or back-end systems and applications to provide the necessary data and information in real-time during a contact center session.

Abstract: Artificial intelligence (AI)-based techniques for determining best action recommendations for issues that arise during the operation of conductor applications and/or robotic process automation (RPA) robots, and for implementing such recommendations, are disclosed. A generative AI model or other type of AI model (e.g., a classifier) is trained to detect issues that occur during operation of such conductor applications and/or RPA robots and to provide recommendations to users with respect to the best action to address the problem. The AI model may list the recommendations that exceed a recommendation threshold, along with their respective confidence scores. In some cases, the AI model may analyze characteristics of executing jobs and provide recommendations for improving the automations, or implement the improvements automatically.

Abstract: Systems and methods for analyzing, prioritizing, and potentially automatically generating robots implementing processes and/or process flows for robotic process automation (RPA) are disclosed. Artificial intelligence (AI) may be used to analyze business processes and/or process flows and look for possible candidates for automation or improvement of existing automations. Listeners (e.g., robots, separate software applications, operating system extensions, etc.) may be employed to listen in the background on user computing systems to mine data pertaining to workflow effectiveness and/or to identify new processes and/or process flows that may improve return on investment (ROI) for RPA.

Abstract: Robot access control and governance for robotic process automation (RPA) is disclosed. A code analyzer of an RPA designer application, such as a workflow analyzer, may read access control and governance policy rules for an RPA designer application and analyze activities of an RPA workflow of the RPA designer application against the access control and governance policy rules. When one or more analyzed activities of the RPA workflow violate the access control and governance policy rules, the code analyzer prevents generation of an RPA robot or publication of the RPA workflow until the RPA workflow satisfies the access control and governance policy rules. When the analyzed activities of the RPA workflow comply with all required access control and governance policy rules, the RPA designer application may generate an RPA robot implementing the RPA workflow or publish the RPA workflow.

Abstract: Some embodiments translate express recurrence in natural language into a time stamp for a subsequent recurrence. In these embodiments, a controller receives a trigger and/or a notification for scheduling a next execution date/time from a user interface or a debugger. A GPT schedule may evaluate the natural language from the trigger or natural language from the notification to compute the next execution date/time. Prompt engineering may then be performed to force the GPT scheduler to execute a schedule based on the next execution date/time.

Abstract: A method is provided. The method is executed by a listener service implemented as a computer program executed by a processor. The listener service provides event listeners for change event management. The method includes initiating the event listeners specific to a target application and specifying change events for the event listeners that occur in the target application. The method also includes receiving, by the listener service from the event listeners, the change events in the target application, based on the specified change events, to capture the change events.

Abstract: Access control and governance for automations is disclosed. A code analyzer of an automation designer application, such as a workflow analyzer, may read access control and governance policy rules for an automation designer application and analyze activities of a workflow, tools, and/or prompts of the automation designer application against the access control and governance policy rules. When one or more analyzed activities of the workflow, one or more tools, and/or one or more prompts violate the access control and governance policy rules, the code analyzer prevents generation of an automation robot or publication of the automation until the workflow, the tools, and/or the prompts satisfy the access control and governance policy rules. When the analyzed activities of the workflow, the tools, and or the prompts comply with all required access control and governance policy rules, the automation designer application may generate an automation or publish the automation.

Abstract: Graphical element search technique selection, fuzzy logic selection for anchors and targets, and hierarchical graphical element identification for robotic process automation (RPA) are disclosed. The fuzzy logic selection of anchors and targets may be part of a larger, tiered, or hierarchical process for identifying graphical elements in the UI. When a selector for a UI element is not found with at least a confidence threshold, similar elements potentially corresponding to the selector for a UI element target may be searched based on fuzzy matching of the target and corresponding anchor(s). Geometric matching may also be employed between the target UI element and its respective anchor(s). The combination of fuzzy matching and geometric matching may allow for more flexible and accurate identification of the exact selector with which an RPA robot is attempting to interact.

Abstract: Using agentic artificial intelligence (AI) to supplement automated information extraction, tool selection and use, and/or tool generation is disclosed. AI agents can use tools to extract information (e.g., names, dates, invoice numbers, etc.) from a source. Tools can be selected, used, and/or generated by an AI agent to perform various tasks. Such as the aforementioned information extraction. In other words, an AI agent can run this process, and AI models themselves may be part of the tools. An AI agent can automatically extract information from a screen and generate an agentic loop or some other kind of self-executing loop that can use a screen as an input, for example.